Claude Code
243 leads from $1,493 of ads
The writer behind the Growth Computer newsletter gave a Claude Code agent $1,500 and full control of a Meta Ads account, then walked away for 31 days. Each morning the only human input was one command; the agent read its own logs, pulled fresh performance data, decided what to create, pause or scale, generated the ad images, built landing page variants, and wrote down its reasoning, more than 5,500 lines over the month.
How it wentIt spent $1,493 of the $1,500 budget and brought in 243 leads at $6.14 each, against a $2.50 target, so by its own goal it missed. Its best ad hit $1.29 per lead on day 12. The single manual change the owner made, adding business-email validation, spiked cost per lead above $50 and the account never fully recovered. Human time was about 2 minutes a day, versus the 1 to 2 hours a day a media buyer would usually spend.
Try it · based on the source's workflow
Run a paid ads test for [my newsletter or product] with a total budget of [amount]. Each day, pull performance from [ads platform], review your past decisions and results, and propose what to create, pause or scale next, with the reason and the numbers behind it. Generate new ad variants in the formats that are already working. Show me the plan and any budget increase before you spend it, and keep a daily log of every decision and result so I can review it.
A starting template based on the workflow the source describes. Review it before you use it; you are responsible for what it does.